Back to skill

Security audit

Ai Video 55eeb0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple AI-video learning note with broad triggers and external video links, but it does not request sensitive access or perform actions on its own.

Before installing, note that the skill may activate on broad AI-video or resource-related phrases. Treat the Bilibili download/tutorial references as third-party content and avoid installing software from unofficial sources unless you independently trust them.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger condition '用户需要ai-video相关帮助' is broad and semantic rather than explicit, so the skill may activate for many ordinary AI-video requests that were not intended to invoke this specific skill. Over-broad activation can route users into unintended workflows, increase exposure to embedded external-resource guidance, and create prompt-scope confusion across unrelated tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The trigger phrase '百宝盒资源' is generic enough to appear in normal conversation, making accidental activation plausible. While not directly enabling code execution, it can cause the agent to enter this skill unexpectedly and follow instructions or references the user did not mean to invoke.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The condition '用户需要ai-video-55eeb0相关帮助' lacks objective boundaries and effectively acts as a catch-all for any request interpreted as related to the skill. This ambiguity increases the chance of unintended skill selection, especially in systems that map loosely related user intent to triggers.

Content

No source excerpt is available for this finding.